Hybrid twins, physics-informed machine learning, augmented intelligence

WORK EXPERIENCE

Research Fellow (June 2023-present) @ CNRS@CREATE

• Researcher at Descartes project
• Data assimilation and hybrid twins for structural health monitoring

Margarita Salas Postdoctoral Researcher (Dec 2022- June 2023) @ ENSAM Paris - University of Zaragoza

Postdoctoral Researcher (2022) @ University of Zaragoza

Visiting Researcher (Sept 2021–March 2022) @ EPFL

Early Stage Researcher (2018–2022) @ University of Zaragoza

Research Assistant (Sept 2014–Jan 2015) @ San Diego State University

EDUCATION

University of Zaragoza (2018–2022) Ph.D. Mechanical Engineering

• Learned simulation as the engine of physical scene understanding. Cum Laude.
• Supervisors: Prof. David González and Prof. Elías Cueto

University of Zaragoza (2015–2017) MSc Industrial Engineering

University of Zaragoza (2011–2015) BSc Mechanical Engineering

TEACHING EXPERIENCE

University of Zaragoza. 240h

• Structures 2. BSc Architecture. 2021/2022.

• Structures 3. BSc Architecture. 2020/21.

• Biostatistics and Numerical Simulation in Bioengineering. MSc Biomedical Engineering. 2020/2021.

• Computational Simulation in Structural Engineering. MSc Industrial Engineering. 2020/2021.

• Structures 1. BSc Architecture. 2019/2020.

• Resistance of materials. BSc Mechanical Engineering. 2019/2020.

• Resistance of materials. BSc Chemical Engineering. 2022/2023.

• Industrial buildings and structural theory. MSc Industrial Engineering. 2022/2023.

• Structural analysis of industrial facilities. BSc Mechanical Engineering 2022/2023.

MASTER THESIS

1. Physics-aware data-driven modelling of biological soft tissues (2021). Nicolás Escribano.

2. Application of Graphic Statics for Structural Design (2023). Sergio Lorente. With honors.

BACHELOR THESIS

1. Design of sustainable structures through parametric calculation and optimization (2022). Sergio Llorente.

2. Generative design of structures using physics-driven artificial intelligence (2023). Guillén Vicente.

VISITING STUDENTS

1. MSc Student: Flavien Alonzo (2019). From École Centrale de Nantes.
2. MSc Student: Gaston Ravanas (2024). From ENS Paris Saclay.

INNOVATION PROGRAMS

1. Teaching innovation project on Graphic Statics. Incorporation of Computational graphic statics in BSc Architecture. Academic Year 2021-2022.

PUBLICATIONS (including open access to papers if available)

• Bermejo-Barbanoj, C., Moya, B., Badías, A., Chinesta, F., & Cueto, E (2024). Super-resolution with thermodynamics-informed neural networks in fluid dynamics problems. Computer Methods in Applied Mechanics and Engineering. IF: 6.9 Q1
• Moya, B., Badías, A., González, D., Chinesta, F., & Cueto, E. (2023). Computational Sensing, Understanding, and Reasoning: An Artificial Intelligence Approach to Physics-Informed World Modelling. Archives of Computational Methods in Engineering, 1-18. IF: 9.7 Q1
• Pichi, F., Moya, B., & Hesthaven, J. S. (2024). A graph convolutional autoencoder approach to model order reduction for parametrized PDEs. Journal of Computational Physics, 501, 112762. IF: 4.645 Q1
• Moya, B., Badías, A., González, D., Chinesta, F., & Cueto, E. (2023). A thermodynamics-informed active learning approach to perception and reasoning about fluids. Computational Mechanics, 1-15. IF: 4.014 Q1
• Moya, B., Badías, A., González, D., Chinesta, F., & Cueto, E. (2022). Physics perception in sloshing scenes with guaranteed thermodynamic consistency. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2), 2136-2150. IF: 16.389 Q1
• Moya, B., Badías, A., Alfaro, I., Chinesta, F., & Cueto, E. (2020). Digital twins that learn and correct themselves. International Journal for Numerical Methods in Engineering. IF: 3.477 Q1
• Moya, B., Alfaro, I., González, D., Chinesta, F., & Cueto, E. (2020). Physically sound, self-learning digital twins for sloshing fluids. PloS one, 15(6), e0234569. IF: 3.240 Q1
• Moya, B., González, D., Alfaro, I., Chinesta, F., & Cueto, E. (2019). Learning slosh dynamics by means of data. Computational Mechanics, 64(2), 511-523. IF: 4.014 Q1

Under review

• Harnessing Hybrid Digital Twinning for Decision-Support in Smart Infrastructures. Liang, H., Moya, B., Chatzi, E., & Chinesta, F.
• Resilience-based post disaster recovery optimization of infrastructure systems using deep reinforcement learning methods. Liang, H., Moya, B., Chatzi, E., & Chinesta, F.
• Unveiling bistable stochastic dynamics through physics-infused learning in scarce and noisy data regimes. Moya, B., Chatzi, E., & Chinesta, F.

Book Chapters

• Chinesta, F., Cueto, E., Grmela, M., Moya, B., Pavelka, M., & Šípka, M. (2020, July). Learning physics from data: a thermodynamic interpretation. In Workshop on Joint Structures and Common Foundations of Statistical Physics, Information Geometry and Inference for Learning (pp. 276-297). Springer, Cham.

Books

• Cueto, E., González, D., Moya, B. (2023) Teorías de estructuras para arquitectos (Structural theory for architechs). Prensas de la Universidad de Zaragoza. In Spanish.

CONFERENCES & PRESENTATIONS

• Physics-informed Generative Adversarial Networks for interactive structural shell design. Eccomas Young Investigators Conference VIII- Oporto, Portugal. 2023.
• Reinforcement for physically sound fluid dynamics correction. CMN 2022 – Las Palmas de Gran Canaria, Spain.
• Thermodynamics of learning physical phenomena. MaxEnt 2022 Paris, France.
• Hybrid twins based on physically sound incremental learning. MMLDT-CSET 2021- San Diego, US; ONLINE. 2021.
• Deep learning of fluid dynamics from free surface data for full state reconstruction and correction. Eccomas Young Investigators Conference VII- Valencia, Spain; ONLINE. 2021.
• Physically sound deep learning development of digital twins from partial measurements of real-world data. Coupled Problems in Engineering 2021- Chia Laguna, Italy; ONLINE.
• Thermodynamics-based learning of fluid dynamics from partial information. Joint European Thermodynamics Conference 2021- Prague, Czech Republic; ONLINE.
• Hybrid twins for fluid applications. World Congress in Computational Mechanics - Paris, France; ONLINE. 2020.
• Manifold Learning of complex fluid behavior for real-time simulation. Eccomas Young Investigators Conference VI- Krakow, Poland. 2019.
• Data-driven learning of slosh dynamics. Congress on Numerical Methods in Engineering- Guimaraes, Portugal. 2019.
• Data-driven, reduced-order modeling and simulation of free-surface flows. Coupled problems in Engineering- Sitges, Spain. 2019.
• Data-based manifold learning of sloshing dynamics. DataBest2019- Paris, France.

KEYNOTES

• Physics-Informed Machine Learning for Characterizing Multistable Stochastic Dynamics. ECCOMAS 2024, Lisbon.
• Thermodynamically admissible reinforcement learning in the development of cognitive digital twins. IUTAM Symposium on Data-Driven Mechanics and Surrogate Modeling 2022. Paris, France.
• Thermodynamics-informed reinforcement learning of fluid dynamics from observation. World Congress in Computational Mechanics and Asian-Pacific Congress on Computational Mechanics (WCCM 2022). Yokohama, Japan; ON LINE

MINISYMPOSIUM ORGANIZATION

• Physical models and reduced order models augmentation with data for physics-informed machine learning in real-world applications. World Congress in Computational Mechanics 2024. Organized together with Marco Tezzele, Annika Robens-Radermacher and Chady Ghnatios.
• Scientific Machine Learning techniques for complex engineering systems. ECCOMAS Young Investigators Conference 20213. Organized together with Matteo Giacomini, Alberto Badías and Filippo Masi.
• Model order reduction and artificial intelligence techniques for surrogate and data-assisted models in computational engineering. ECCOMAS Young Investigators Conference 2021. Organized together with Matteo Giacomini and Alberto Badías.

PROJECTS & FUNDING

• Margarita Salas fellowship. Self-funded NEXT GEN project by University of Zaragoza and Ministry of Science. Dec 2022 - Dec 2024.

• Ibercaja Scholarship for International Research stays. 2021.

• FPI fellowship for PhD research funding. Spanish Ministry of Science. 2019-2022.

AWARDS

Award to best Teaching innovation project by Chair Banco Santander (University of Zaragoza)

• Tercer Milenio Young Researchers Talent Award, awarded by Heraldo de Aragon. “This award is given to young researchers (under 35 years of age) who develop their activity in science and technology. To stimulate new talents born or trained in Aragon, the award will be given to profiles whose emerging trajectory stands out specially or has a significant potential”. 2022.

• Finalist Arts&Science Contest at WCCM 2020 with “Figments of reality”.

• Torres de Miguel Award. Award to the best project. Given by the Official Engineering Association of Aragon, Navarra, and La Rioja. Zaragoza (Spain). 2018.

• San Diego State University Dean’s List Fall 2014 and Spring 2015. The Dean’s List recognizes academic achievement within a single semester or semester.

• ‘America, Asia and Oceania’ Scholarship for bachelor international studies out of Europe by the University of Zaragoza. 2014-2015.

• Fellowship of good academic standing for language immersion in Canada, given by the Regional Government of Aragon (Spain). 2011.

PROFFESIONAL ENGAGEMENT

GUEST EDITOR

Guest editor in chief in collection Advances in Machine Learning and Computational Mechanics (https://www.springeropen.com/collections/AMLCM ) in Advanced Modeling and Simulation in Engineering Sciences. Due date submissions Aug 15th, 2024.

ROLES

Coordinator of the Young Researchers Section of the Spanish Society of Computational Mechanics and Computational Engineering (SEMNI). (June 2024-present)

• Board member of the Young Researchers Section of the Spanish Society of Computational Mechanics and Computational Engineering (SEMNI). (June 2022-present)

• Member of the Scientific Commission at the University of Zaragoza. Elected as representative of the doctoral alumni. 2020-2022.

• Member of the Scientific Commission at the University of Zaragoza. Elected as representative of the doctoral alumni. 2020-2022.

• Member of the Ph. D. program on Mechanical Engineering at the University of Zaragoza. 2020-2022.

• Member of Quality Commission. Ph. D. program in Mechanical Engineering at the University of Zaragoza. 2020-2022.

AFFILIATIONS

• Member of the Young Researchers Section of the Spanish Society of Computational Mechanics and Computational Engineering (SEMNI)

OUTREACH COMMUNICATION

NEWEST

• Video on Innovation teaching program to include graphic statics in the engineering curriculum https://www.youtube.com/watch?v=YAvVp5u4zNI

• Open platform for learning by interaction of graphic statics https://sergiolc2000.github.io/paginaweb-estaticagrafica/

• Participation in the European Researchers’ Night (2019, 2020, 2021): https://www.youtube.com/watch?v=Wu2KVFctSBI&t=51s
• Radio interview: https://www.ivoox.com/mananas-onda-aragonesa-el-gemelo-audios-mp3_rf_58255616_1.html
• Participation and finalist of the contest “Explain your thesis in 20 tweets”. https://twitter.com/BeatrizMoyaG/status/1381539927914131456?s=20&t=UHsEsgLlPSoi1I0KGZaYxA
• Finalist in Arts and Science contest in the 2020 World Congress in Computational Mechanics with the picture Figments of reality. https://twitter.com/beatrizmoyag/status/1346065933803139072
• Participation in the program “A woman engineer in every school”, giving talks to young children, and additional talks for children in schools (11F ACTIONS): https://aragonuniversidad.es/universidad/cerca-de-800-alumnos-de-primaria-de-aragon-debaten-con-los-investigadores-como-sera-la-vida-en-2075/
• Article in the local press: Aprender a razonar, el ser o no ser de la robótica (Learning to reason, the to be or not to be of robotics). Heraldo de Aragón. https://www.heraldo.es/noticias/aragon/2021/11/20/aprender-a-razonar-el-ser-o-no-ser-de-la-robotica-1534983.html
• Videos : ** Self-learning digital twins for sloshing fluids. https://www.youtube.com/watch?v=d1JyhPNkLkU ** Physics perception in sloshing scenes. https://www.youtube.com/watch?v=Qlb1VpWRVaQ ** Physics-informed Reinforcement Learning for perception and reasoning about fluids. https://www.youtube.com/watch?v=ikPgZMpsCFk
• Science stand-up comedy courses to perform at events for the general public.
• Talk in Circular engineering series in middle schools (2023)